Scholarlink

<p>The rapid integration of artificial intelligence (AI) and machine learning (ML) into medical devices has underscored the need for transparency in regulatory reporting. In 2021, the U.S. Food and Drug Administration (FDA) issued Good Machine Learning Practice (GMLP) principles, but adherence in FDA-reviewed devices remains uncertain. We reviewed 1,012 summaries of safety and effectiveness (SSEDs) for AI/ML-enabled devices approved or cleared by the FDA between 1970 and December 2024. Transparency in model development and performance was assessed using a novel AI Characteristics Transparency Reporting (ACTR) score across 17 categories. The average ACTR score was 3.3 out of 17, with modest improvement by 0.88 points (95% CI, 0.54–1.23) after the 2021 guidelines. Nearly half of devices did not report a clinical study and over half did not report any performance metric. These findings highlight transparency gaps and emphasize the need for enforceable standards to ensure trust in AI/ML medical technologies.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Evaluating transparency in AI/ML model characteristics for FDA-reviewed medical devices

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月17日

查看全文
  • Viraj Mehta,
  • Abhinav Komanduri,
  • Rishabh Singh Bhadouriya,
  • Vilina Mehta,
  • Michael David Johnson,
  • Priyanka Shrestha,
  • Margaret Nikolov,
  • Bhav Jain,
  • Nigam Shah,
  • Kevin Schulman

摘要

The rapid integration of artificial intelligence (AI) and machine learning (ML) into medical devices has underscored the need for transparency in regulatory reporting. In 2021, the U.S. Food and Drug Administration (FDA) issued Good Machine Learning Practice (GMLP) principles, but adherence in FDA-reviewed devices remains uncertain. We reviewed 1,012 summaries of safety and effectiveness (SSEDs) for AI/ML-enabled devices approved or cleared by the FDA between 1970 and December 2024. Transparency in model development and performance was assessed using a novel AI Characteristics Transparency Reporting (ACTR) score across 17 categories. The average ACTR score was 3.3 out of 17, with modest improvement by 0.88 points (95% CI, 0.54–1.23) after the 2021 guidelines. Nearly half of devices did not report a clinical study and over half did not report any performance metric. These findings highlight transparency gaps and emphasize the need for enforceable standards to ensure trust in AI/ML medical technologies.